import numpy as np
import pandas as pd
from itertools import cycle
from scipy import interp

# sklearn
from sklearn import metrics
from sklearn.model_selection import train_test_split, StratifiedShuffleSplit
from sklearn import datasets
from sklearn.preprocessing import StandardScaler
from sklearn import preprocessing

# TensorFlow
import tensorflow as tf

# Visualisation libraries

## Text
from colorama import Fore, Back, Style
from IPython.display import Image, display, Markdown, Latex, clear_output

## progressbar
import progressbar

## plotly
from plotly.offline import init_notebook_mode, iplot 
import plotly.graph_objs as go
import plotly.offline as py
from plotly.subplots import make_subplots
import plotly.express as px

## seaborn
import seaborn as sns

## matplotlib
import matplotlib.pyplot as plt
from matplotlib.patches import Ellipse, Polygon
from matplotlib.font_manager import FontProperties
import matplotlib.colors as mcolors
from matplotlib import cm
plt.style.use('seaborn-whitegrid')
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12
plt.rcParams['text.color'] = 'k'
%matplotlib inline

import warnings
warnings.filterwarnings("ignore")

Home / Deep Learning

Tensorflow Classifiers

• Tensorflow Linear Classifier
• Tensorflow DNN Classifier
• Tensorflow Boosted Trees Classifier
• Tensorflow Boosted Trees Classifier with Feature Importance Analysis

In this article, we demonstrate implementing the Tensorflow Linear classifier model by an example. The details regarding this dataset can be found in the Diagnostic Wisconsin Breast Cancer Database.

Dataset

data = datasets.load_breast_cancer()
Data = pd.DataFrame(data['data'], columns = [x.title() for x in data['feature_names']])
Labels_dict = dict(zip(list(np.sort(np.unique(data['target'].tolist()))),
                       list([x.title() for x in data['target_names']])))
Target = 'Diagnosis'
Data[Target] = data['target']
# Data['Diagnosis'] = data['target'].replace(Labels_dict)
display(Data)
print(data['DESCR'])

	Mean Radius	Mean Texture	Mean Perimeter	Mean Area	Mean Smoothness	Mean Compactness	Mean Concavity	Mean Concave Points	Mean Symmetry	Mean Fractal Dimension	...	Worst Texture	Worst Perimeter	Worst Area	Worst Smoothness	Worst Compactness	Worst Concavity	Worst Concave Points	Worst Symmetry	Worst Fractal Dimension	Diagnosis
0	17.99	10.38	122.80	1001.0	0.11840	0.27760	0.30010	0.14710	0.2419	0.07871	...	17.33	184.60	2019.0	0.16220	0.66560	0.7119	0.2654	0.4601	0.11890	0
1	20.57	17.77	132.90	1326.0	0.08474	0.07864	0.08690	0.07017	0.1812	0.05667	...	23.41	158.80	1956.0	0.12380	0.18660	0.2416	0.1860	0.2750	0.08902	0
2	19.69	21.25	130.00	1203.0	0.10960	0.15990	0.19740	0.12790	0.2069	0.05999	...	25.53	152.50	1709.0	0.14440	0.42450	0.4504	0.2430	0.3613	0.08758	0
3	11.42	20.38	77.58	386.1	0.14250	0.28390	0.24140	0.10520	0.2597	0.09744	...	26.50	98.87	567.7	0.20980	0.86630	0.6869	0.2575	0.6638	0.17300	0
4	20.29	14.34	135.10	1297.0	0.10030	0.13280	0.19800	0.10430	0.1809	0.05883	...	16.67	152.20	1575.0	0.13740	0.20500	0.4000	0.1625	0.2364	0.07678	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
564	21.56	22.39	142.00	1479.0	0.11100	0.11590	0.24390	0.13890	0.1726	0.05623	...	26.40	166.10	2027.0	0.14100	0.21130	0.4107	0.2216	0.2060	0.07115	0
565	20.13	28.25	131.20	1261.0	0.09780	0.10340	0.14400	0.09791	0.1752	0.05533	...	38.25	155.00	1731.0	0.11660	0.19220	0.3215	0.1628	0.2572	0.06637	0
566	16.60	28.08	108.30	858.1	0.08455	0.10230	0.09251	0.05302	0.1590	0.05648	...	34.12	126.70	1124.0	0.11390	0.30940	0.3403	0.1418	0.2218	0.07820	0
567	20.60	29.33	140.10	1265.0	0.11780	0.27700	0.35140	0.15200	0.2397	0.07016	...	39.42	184.60	1821.0	0.16500	0.86810	0.9387	0.2650	0.4087	0.12400	0
568	7.76	24.54	47.92	181.0	0.05263	0.04362	0.00000	0.00000	0.1587	0.05884	...	30.37	59.16	268.6	0.08996	0.06444	0.0000	0.0000	0.2871	0.07039	1

569 rows × 31 columns

.. _breast_cancer_dataset:

Breast cancer wisconsin (diagnostic) dataset
--------------------------------------------

**Data Set Characteristics:**

    :Number of Instances: 569

    :Number of Attributes: 30 numeric, predictive attributes and the class

    :Attribute Information:
        - radius (mean of distances from center to points on the perimeter)
        - texture (standard deviation of gray-scale values)
        - perimeter
        - area
        - smoothness (local variation in radius lengths)
        - compactness (perimeter^2 / area - 1.0)
        - concavity (severity of concave portions of the contour)
        - concave points (number of concave portions of the contour)
        - symmetry
        - fractal dimension ("coastline approximation" - 1)

        The mean, standard error, and "worst" or largest (mean of the three
        worst/largest values) of these features were computed for each image,
        resulting in 30 features.  For instance, field 0 is Mean Radius, field
        10 is Radius SE, field 20 is Worst Radius.

        - class:
                - WDBC-Malignant
                - WDBC-Benign

    :Summary Statistics:

    ===================================== ====== ======
                                           Min    Max
    ===================================== ====== ======
    radius (mean):                        6.981  28.11
    texture (mean):                       9.71   39.28
    perimeter (mean):                     43.79  188.5
    area (mean):                          143.5  2501.0
    smoothness (mean):                    0.053  0.163
    compactness (mean):                   0.019  0.345
    concavity (mean):                     0.0    0.427
    concave points (mean):                0.0    0.201
    symmetry (mean):                      0.106  0.304
    fractal dimension (mean):             0.05   0.097
    radius (standard error):              0.112  2.873
    texture (standard error):             0.36   4.885
    perimeter (standard error):           0.757  21.98
    area (standard error):                6.802  542.2
    smoothness (standard error):          0.002  0.031
    compactness (standard error):         0.002  0.135
    concavity (standard error):           0.0    0.396
    concave points (standard error):      0.0    0.053
    symmetry (standard error):            0.008  0.079
    fractal dimension (standard error):   0.001  0.03
    radius (worst):                       7.93   36.04
    texture (worst):                      12.02  49.54
    perimeter (worst):                    50.41  251.2
    area (worst):                         185.2  4254.0
    smoothness (worst):                   0.071  0.223
    compactness (worst):                  0.027  1.058
    concavity (worst):                    0.0    1.252
    concave points (worst):               0.0    0.291
    symmetry (worst):                     0.156  0.664
    fractal dimension (worst):            0.055  0.208
    ===================================== ====== ======

    :Missing Attribute Values: None

    :Class Distribution: 212 - Malignant, 357 - Benign

    :Creator:  Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian

    :Donor: Nick Street

    :Date: November, 1995

This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.
https://goo.gl/U2Uwz2

Features are computed from a digitized image of a fine needle
aspirate (FNA) of a breast mass.  They describe
characteristics of the cell nuclei present in the image.

Separating plane described above was obtained using
Multisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree
Construction Via Linear Programming." Proceedings of the 4th
Midwest Artificial Intelligence and Cognitive Science Society,
pp. 97-101, 1992], a classification method which uses linear
programming to construct a decision tree.  Relevant features
were selected using an exhaustive search in the space of 1-4
features and 1-3 separating planes.

The actual linear program used to obtain the separating plane
in the 3-dimensional space is that described in:
[K. P. Bennett and O. L. Mangasarian: "Robust Linear
Programming Discrimination of Two Linearly Inseparable Sets",
Optimization Methods and Software 1, 1992, 23-34].

This database is also available through the UW CS ftp server:

ftp ftp.cs.wisc.edu
cd math-prog/cpo-dataset/machine-learn/WDBC/

.. topic:: References

   - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction 
     for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on 
     Electronic Imaging: Science and Technology, volume 1905, pages 861-870,
     San Jose, CA, 1993.
   - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and 
     prognosis via linear programming. Operations Research, 43(4), pages 570-577, 
     July-August 1995.
   - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques
     to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) 
     163-171.

As can be seen, the number of instances is 569 and the number of attributes is 32. The object of the exercise is to create a classification model that can classify the type of Diagnosis base on the rest of the attributes. However, first, let's plot a count plot for Diagnosis attribute.

Features with high variance

Moreover, high variance for some features can hurt our modeling process. For this reason, we would like to standardize features by removing the mean and scaling to unit variance.

def Feature_Normalize(X, PD):
    def List_Break(mylist, n = PD['word_break']):
        Out = []
        for x in mylist:
            y = x.split()
            if len(y)> n:
                z = ' '.join(y[:n])
                sep = np.arange(0, len(y), n)[1:]
                for n in sep:
                    z = z + '\n'+ ' '.join(y[n:])
            else:
                z = ' '.join(y)
            Out.append(z)
        return Out

    X = Data.drop(columns = [Target])
    y = Data[Target]

    scaler = preprocessing.StandardScaler()
    X_std = scaler.fit_transform(X)
    X_std = pd.DataFrame(data = X_std, columns = X.columns)

    fig, ax = plt.subplots(2, 1, figsize = PD['figsize'])
    ax = ax.ravel()
    CP = [sns.color_palette("OrRd", 20), sns.color_palette("Greens", X.shape[1])]
    Names = ['Variance of the Features', 'Variance of the Features (Standardized)']
    Sets = [X, X_std]
    kws = dict(label='Feature\nVariance', aspect=10, shrink= .3)
    for i in range(len(ax)):
        Temp = Sets[i].var().sort_values(ascending = False).to_frame(name= 'Variance').round(2).T
        _ = sns.heatmap(Temp, ax=ax[i], annot=True, square=True,  cmap = CP[i],
                        linewidths = 0.8, vmin=0, vmax=Temp.max(axis =1)[0],  annot_kws={"size": PD['annot_text_size']},
                        cbar_kws=kws)
        if not PD['word_break'] == None:
            mylist = List_Break(Temp.T.index.tolist())
            _ = ax[i].xaxis.set_ticklabels(mylist)
        _ = ax[i].set_yticklabels('')
        _ = ax[i].set_title(Names[i], weight='bold', fontsize = 14)
        _ = ax[i].set_aspect(1)
        del Temp
    plt.subplots_adjust(hspace=PD['hspace'])
    Out = pd.DataFrame(data = X_std, columns = X.columns.tolist())
    return Out

X = Data.drop(columns = [Target])
y = Data[Target]

PD = dict(figsize = (20, 8), hspace = 0.2, annot_text_size = 8, word_break = None)
X = Feature_Normalize(X, PD)

Train and Test sets

def DatasetTargetDist(Inp, Target, Labels_dict, PD):
    # Table
    Table = Inp[Target].value_counts().to_frame('Count').reset_index(drop = False).rename(columns = {'index':Target})
    Table[Target] = Table[Target].replace(Labels_dict)
    Table['Percentage'] = np.round(100*(Table['Count']/Table['Count'].sum()),2)
    fig = make_subplots(rows=1, cols=2, horizontal_spacing = 0.02, column_widths=PD['column_widths'],
                        specs=[[{"type": "table"},{"type": "pie"}]])

    # Right
    fig.add_trace(go.Pie(labels=Table[Target].values, values=Table['Count'].values,
                         pull=PD['pull'], textfont=dict(size= PD['textfont']),
                         marker=dict(colors = PD['PieColors'], line=dict(color='black', width=1))), row=1, col=2)
    fig.update_traces(hole=PD['hole'])
    fig.update_layout(height = PD['height'], legend=dict(orientation="v"), legend_title_text= PD['legend_title'])
    
    # Left
    T = Table.copy()
    T['Percentage'] = T['Percentage'].map(lambda x: '%%%.2f' % x)
    Temp = []
    for i in T.columns:
        Temp.append(T.loc[:,i].values)

    fig.add_trace(go.Table(header=dict(values = list(Table.columns), line_color='darkslategray',
                                       fill_color= PD['TableColors'][0], align=['center','center'],
                                       font=dict(color='white', size=12), height=25), columnwidth = PD['tablecolumnwidth'],
                           cells=dict(values=Temp, line_color='darkslategray',
                                      fill=dict(color= [PD['TableColors'][1], PD['TableColors'][1]]),
                                  align=['center', 'center'], font_size=12, height=20)), 1, 1)

    fig.update_layout(title={'text': '<b>' + Target + '<b>', 'x':PD['title_x'],
                                     'y':PD['title_y'], 'xanchor': 'center', 'yanchor': 'top'})
    fig.show()

Pull = [0 for x in range((len(Labels_dict)-1))]
Pull.append(.05)
PD = dict(PieColors = ['SeaGreen','FireBrick'],
          TableColors = ['Navy','White'], hole = .4,
          column_widths=[0.6, 0.4],textfont = 14, height = 350, tablecolumnwidth = [0.20, 0.12, 0.15],
          pull = Pull, legend_title = Target, title_x = 0.5, title_y = 0.8)
del Pull
DatasetTargetDist(Data, Target, Labels_dict, PD)

StratifiedKFold is a variation of k-fold which returns stratified folds: each set contains approximately the same percentage of samples of each target class as the complete set.

Test_Size = 0.3
sss = StratifiedShuffleSplit(n_splits=1, test_size=Test_Size, random_state=42)
_ = sss.get_n_splits(X, y)
# For Tensorflow
X.columns = [x.replace(' ','_') for x in X.columns]

for train_index, test_index in sss.split(X, y):
    # X
    if isinstance(X, pd.DataFrame):
        X_train, X_test = X.loc[train_index], X.loc[test_index]
    else:
        X_train, X_test = X[train_index], X[test_index]
    # y    
    if isinstance(y, pd.Series):
        y_train, y_test = y[train_index], y[test_index]
    else:
        y_train, y_test = y[train_index], y[test_index]
del sss

def Train_Test_Dist(X_train, y_train, X_test, y_test, PD, Labels_dict = Labels_dict):
    def ToSeries(x):
        if not isinstance(x, pd.Series):
            Out = pd.Series(x)
        else:
            Out = x.copy()
        return Out
    
    fig = make_subplots(rows=1, cols=3, horizontal_spacing = 0.02, column_widths= PD['column_widths'],
                        specs=[[{"type": "table"},{'type':'domain'}, {'type':'domain'}]])
    # Right
    C = 2
    for y in [ToSeries(y_train).replace(Labels_dict), ToSeries(y_test).replace(Labels_dict)]:
        fig.add_trace(go.Pie(labels= list(Labels_dict.values()),
                             values= y.value_counts().values, pull=PD['pull'],
                             textfont=dict(size=PD['textfont']),
                             marker=dict(colors = PD['PieColors'],
                             line=dict(color='black', width=1))), row=1, col=C)
        fig.update_traces(hole=.5)
        fig.update_layout(legend=dict(orientation="v"), legend_title_text= PD['legend_title'])
        C+=1
    
    # Left
    
    # Table
    Table = pd.DataFrame(data={'Set':['X_train','X_test','y_train','y_test'],
                       'Shape':[X_train.shape, X_test.shape, y_train.shape, y_test.shape]}).astype(str)
    T = Table.copy()
    Temp = []
    for i in T.columns:
        Temp.append(T.loc[:,i].values)
        
    TableColors = PD['TableColors']
    fig.add_trace(go.Table(header=dict(values = list(Table.columns), line_color='darkslategray',
                                       fill_color= TableColors[0], align=['center','center'],
                                       font=dict(color='white', size=12), height=25), columnwidth = PD['tablecolumnwidth'],
                           cells=dict(values=Temp, line_color='darkslategray',
                                      fill=dict(color= [TableColors[1], TableColors[1]]),
                                  align=['center', 'center'], font_size=12, height=20)), 1, 1)
    fig.update_layout(title={'text': '<b>' + 'Dataset Distribution' + '<b>', 'x':PD['title_x'],
                                     'y':PD['title_y'], 'xanchor': 'center', 'yanchor': 'top'})
    if not PD['height'] == None:
        fig.update_layout(height = PD['height'])
    fig.show()
    
PD.update(dict(PieColors = ['FireBrick', 'SeaGreen'], column_widths=[0.3, 0.3, 0.3],
               tablecolumnwidth = [0.2, 0.4], height = 350, legend_title = Target))

Train_Test_Dist(X_train, y_train, X_test, y_test, PD)

Modeling: Tensorflow Linear Classifier

Here, we use the Tensorflow Linear classifier model.tf.estimator.LinearClassifier.

Input Function

The input function specifies how data is converted to a tf.data.Dataset that feeds the input pipeline in a streaming fashion. Moreover, an input function is a function that returns a tf.data.Dataset object which outputs the following two-element tuple:

• features - A Python dictionary in which:
  • Each key is the name of a feature.
  • Each value is an array containing all of that feature's values.
• label - An array containing the values of the label for every example.

def input_fn(features, labels, training=True, batch_size=256):
    """An input function for training or evaluating"""
    # Convert the inputs to a Dataset.
    dataset = tf.data.Dataset.from_tensor_slices((dict(features), labels))

    # Shuffle and repeat if you are in training mode.
    if training:
        dataset = dataset.shuffle(1000).repeat()
    
    return dataset.batch(batch_size)

Moreover, an estimator model consists of two main parts, feature columns, and a numeric vector. Feature columns provide explanations for the input numeric vector. The following function separates categorical and numerical columns (features)and returns a descriptive list of feature columns.

def Feat_Columns(Inp):
    Temp = Inp.dtypes.reset_index(drop = False)
    Temp.columns = ['Features', 'Data Type']
    Temp['Data Type'] = Temp['Data Type'].astype(str)
    # Numeric_Columns
    Numeric_Columns = Temp.loc[Temp['Data Type'].isin(['int64', 'int32', 'float64', 'float32']),'Features'].tolist()
    # Categorical_Columns
    Categorical_Columns = Temp.loc[Temp['Data Type'] == 'object','Features'].tolist()
        
    # Feature Columns
    feature_columns = []
    if len(Categorical_Columns)>0:
        for feature_name in Categorical_Columns:
          vocabulary = Inp[feature_name].unique()
          feature_columns.append(tf.feature_column.categorical_column_with_vocabulary_list(feature_name, vocabulary))
    if len(Numeric_Columns)>0:
        for feature_name in Numeric_Columns:
          feature_columns.append(tf.feature_column.numeric_column(feature_name))
    return feature_columns

my_feature_columns = Feat_Columns(X)

Estimator using the Default Optimizer

tf.keras.backend.clear_session()
IT = int(5e3)
classifier = tf.estimator.LinearClassifier(feature_columns=my_feature_columns)
classifier.train(input_fn=lambda: input_fn(X_train, y_train, training=True), max_steps = IT)
result = classifier.evaluate(input_fn=lambda: input_fn(X_test, y_test, training=False))
clear_output()
display(pd.DataFrame(result, index = ['']).round(4))

	accuracy	accuracy_baseline	auc	auc_precision_recall	average_loss	label/mean	loss	precision	prediction/mean	recall	global_step
	0.9766	0.6257	0.9974	0.9984	0.0584	0.6257	0.0584	0.9725	0.6232	0.9907	5000

ROC Curves

def ROC_Curve(y_test, probs, n_classes, FS = 7, ax = False, pad = 0.01):
    # converting y_test to categorical
    y_test_cat = tf.keras.utils.to_categorical(y_test, num_classes=n_classes, dtype='float32')
    # Compute ROC curve and ROC area for each class
    fpr = dict()
    tpr = dict()
    roc_auc = dict()
    for i in range(n_classes):
        fpr[i], tpr[i], _ = metrics.roc_curve(y_test_cat[:, i], probs[:, i])
        roc_auc[i] = metrics.auc(fpr[i], tpr[i])

    # Compute micro-average ROC curve and ROC area
    fpr["micro"], tpr["micro"], _ = metrics.roc_curve(y_test_cat.ravel(), probs.ravel())
    roc_auc["micro"] = metrics.auc(fpr["micro"], tpr["micro"])

    # First aggregate all false positive rates
    all_fpr = np.unique(np.concatenate([fpr[i] for i in range(n_classes)]))

    # Then interpolate all ROC curves at this points
    mean_tpr = np.zeros_like(all_fpr)
    for i in range(n_classes):
        mean_tpr += interp(all_fpr, fpr[i], tpr[i])

    # Finally average it and compute AUC
    mean_tpr /= n_classes

    fpr["macro"] = all_fpr
    tpr["macro"] = mean_tpr
    roc_auc["macro"] = metrics.auc(fpr["macro"], tpr["macro"])

    fig = go.Figure()
    fig.add_trace(go.Scatter(x=[0, 1], y=[0, 1], name = 'FPR = TPR', line = dict(color='Black', width=2, dash='dash')))
    fig.add_trace(go.Scatter(x=fpr["micro"], y=tpr["micro"], mode='lines', marker_color = 'deeppink',
                             name='micro-average ROC curve (area = {0:0.2f})'.format(roc_auc["micro"])))
    fig.add_trace(go.Scatter(x=fpr["macro"], y=tpr["macro"], mode='lines', marker_color = 'navy',
                             name='macro-average ROC curve (area = {0:0.2f})'.format(roc_auc["macro"])))

    colors = cycle(['Aqua', 'DarkOrange', 'CornflowerBlue'])
    for i, color in zip(range(n_classes), colors):
        _ = fig.add_trace(go.Scatter(x = fpr[i], y = tpr[i], mode='lines', marker_color= px.colors.sequential.Rainbow,
                                     name='ROC curve of class {0} (area = {1:0.2f})'.format(i, roc_auc[i])))

    # Background
    fig.update_layout(plot_bgcolor= 'white')
    fig.update_xaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray', range =[-pad, 1+pad],
                     title = 'False Positive Rate (FPR)')
    fig.update_yaxes(showline=True, linewidth=1, linecolor='Lightgray', mirror=True,
                     zeroline=True, zerolinewidth=1, zerolinecolor='Black',
                     showgrid=True, gridwidth=1, gridcolor='Lightgray', range =[-pad, 1+pad],
                     title = 'True Positive Rate (TPR)')
    fig.update_yaxes(scaleanchor = "x", scaleratio = 1)
    fig.update_layout(height = 600, width = 810)
    fig.update_layout(title={'text': '<b>' + 'Receiver Operating Characteristic (ROC) Curves' + '<b>', 'x': .5,
                                         'y': .9, 'xanchor': 'center', 'yanchor': 'top'})
    fig.show()

pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_test, y_test, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])    
ROC_Curve(y_test, probs, n_classes = len(Labels_dict), FS = 8)

Confusion Matrix

The confusion matrix allows for visualization of the performance of an algorithm. Note that due to the size of data, here we don't provide a Cross-validation evaluation. In general, this type of evaluation is preferred.

def Confusion_Mat(CM_Train, CM_Test, PD, n_splits = 10):
    if n_splits == None:
        Titles = ['Train Set', 'Test Set']
    else:
        Titles = ['Train Set (CV = % i)' % n_splits, 'Test Set (CV = % i)' % n_splits]
    CM = [CM_Train, CM_Test]
    Cmap = ['Greens', 'YlGn','Blues', 'PuBu']
    for i in range(2):
        fig, ax = plt.subplots(1, 2, figsize= PD['FS'])
        fig.suptitle(Titles[i], weight = 'bold', fontsize = 16)
        _ = sns.heatmap(CM[i], annot=True, annot_kws={"size": PD['annot_kws']}, cmap=Cmap[2*i], ax = ax[0],
                        linewidths = 0.2, cbar_kws={"shrink": PD['shrink']})
        _ = ax[0].set_title('Confusion Matrix');
        Temp = np.round(CM[i].astype('float') / CM[i].sum(axis=1)[:, np.newaxis], 2)
        _ = sns.heatmap(Temp,
                        annot=True, annot_kws={"size": PD['annot_kws']}, cmap=Cmap[2*i+1], ax = ax[1],
                       linewidths = 0.4, vmin=0, vmax=1, cbar_kws={"shrink": PD['shrink']})
        _ = ax[1].set_title('Normalized Confusion Matrix');

        for a in ax:
            _ = a.set_xlabel('Predicted labels')
            _ = a.set_ylabel('True labels'); 
            _ = a.xaxis.set_ticklabels(PD['Labels'])
            _ = a.yaxis.set_ticklabels(PD['Labels'])
            _ = a.set_aspect(1)

# Train
pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_train, y_train, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])
y_pred = np.argmax(probs, axis = 1).reshape(-1,1)
Reports_Train = pd.DataFrame(metrics.classification_report(y_train, y_pred, target_names=list(Labels_dict.values()),
                                                           output_dict=True)).T
CM_Train = metrics.confusion_matrix(y_train, y_pred)
# Test
pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_test, y_test, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])
y_pred = np.argmax(probs, axis = 1).reshape(-1,1)
Reports_Test = pd.DataFrame(metrics.classification_report(y_test, y_pred, target_names=list(Labels_dict.values()),
                                                          output_dict=True)).T
CM_Test = metrics.confusion_matrix(y_test, y_pred)

Reports_Train = Reports_Train.reset_index().rename(columns ={'index': 'Train Set'})
Reports_Test = Reports_Test.reset_index().rename(columns ={'index': 'Test Set'})
                                                 
display(Reports_Train.style.hide_index().set_properties(**{'background-color': 'HoneyDew', 'color': 'Black'}).\
        set_properties(subset=['Train Set'], **{'background-color': 'SeaGreen', 'color': 'White'}))
display(Reports_Test.style.hide_index().set_properties(**{'background-color': 'Azure', 'color': 'Black'}).\
        set_properties(subset=['Test Set'], **{'background-color': 'RoyalBlue', 'color': 'White'}))

PD = dict(FS = (10, 6), annot_kws = 14, shrink = .6, Labels = list(Labels_dict.values()))
Confusion_Mat(CM_Train, CM_Test, PD = PD, n_splits = None)

Train Set	precision	recall	f1-score	support
Malignant	0.993151	0.979730	0.986395	148.000000
Benign	0.988095	0.996000	0.992032	250.000000
accuracy	0.989950	0.989950	0.989950	0.989950
macro avg	0.990623	0.987865	0.989213	398.000000
weighted avg	0.989975	0.989950	0.989936	398.000000

Test Set	precision	recall	f1-score	support
Malignant	0.983871	0.953125	0.968254	64.000000
Benign	0.972477	0.990654	0.981481	107.000000
accuracy	0.976608	0.976608	0.976608	0.976608
macro avg	0.978174	0.971890	0.974868	171.000000
weighted avg	0.976741	0.976608	0.976531	171.000000

Estimator using the FTRL Optimizer with Regularization

The Follow the Regularized Leader (FTRL) model is an implementation of the FTRL-Proximal online learning algorithm for binomial logistic regression (for details see [6]).

tf.keras.backend.clear_session()
IT = int(5e3)
classifier = tf.estimator.LinearClassifier(feature_columns=my_feature_columns,
                          optimizer=tf.keras.optimizers.Ftrl(learning_rate=0.1, l1_regularization_strength=0.001))
#
classifier.train(input_fn=lambda: input_fn(X_train, y_train, training=True), max_steps = IT)
result = classifier.evaluate(input_fn=lambda: input_fn(X_test, y_test, training=False))
clear_output()
display(pd.DataFrame(result, index = ['']).round(4))

	accuracy	accuracy_baseline	auc	auc_precision_recall	average_loss	label/mean	loss	precision	prediction/mean	recall	global_step
	0.9825	0.6257	0.9978	0.9986	0.0554	0.6257	0.0554	0.9906	0.6165	0.9813	5000

ROC Curves

pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_test, y_test, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])    
ROC_Curve(y_test, probs, n_classes = len(Labels_dict), FS = 8)

Confusion Matrix

# Train
pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_train, y_train, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])
y_pred = np.argmax(probs, axis = 1).reshape(-1,1)
Reports_Train = pd.DataFrame(metrics.classification_report(y_train, y_pred, target_names=list(Labels_dict.values()),
                                                           output_dict=True)).T
CM_Train = metrics.confusion_matrix(y_train, y_pred)
# Test
pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_test, y_test, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])
y_pred = np.argmax(probs, axis = 1).reshape(-1,1)
Reports_Test = pd.DataFrame(metrics.classification_report(y_test, y_pred, target_names=list(Labels_dict.values()),
                                                          output_dict=True)).T
CM_Test = metrics.confusion_matrix(y_test, y_pred)

Reports_Train = Reports_Train.reset_index().rename(columns ={'index': 'Train Set'})
Reports_Test = Reports_Test.reset_index().rename(columns ={'index': 'Test Set'})
                                                 
display(Reports_Train.style.hide_index().set_properties(**{'background-color': 'HoneyDew', 'color': 'Black'}).\
        set_properties(subset=['Train Set'], **{'background-color': 'SeaGreen', 'color': 'White'}))
display(Reports_Test.style.hide_index().set_properties(**{'background-color': 'Azure', 'color': 'Black'}).\
        set_properties(subset=['Test Set'], **{'background-color': 'RoyalBlue', 'color': 'White'}))

PD = dict(FS = (10, 6), annot_kws = 14, shrink = .6, Labels = list(Labels_dict.values()))
Confusion_Mat(CM_Train, CM_Test, PD = PD, n_splits = None)

Train Set	precision	recall	f1-score	support
Malignant	0.993151	0.979730	0.986395	148.000000
Benign	0.988095	0.996000	0.992032	250.000000
accuracy	0.989950	0.989950	0.989950	0.989950
macro avg	0.990623	0.987865	0.989213	398.000000
weighted avg	0.989975	0.989950	0.989936	398.000000

Test Set	precision	recall	f1-score	support
Malignant	0.969231	0.984375	0.976744	64.000000
Benign	0.990566	0.981308	0.985915	107.000000
accuracy	0.982456	0.982456	0.982456	0.982456
macro avg	0.979898	0.982842	0.981330	171.000000
weighted avg	0.982581	0.982456	0.982483	171.000000

Estimator using an Optimizer with a Learning Rate Decay

tf.keras.backend.clear_session()
IT = int(5e3)
classifier = tf.estimator.LinearClassifier(feature_columns=my_feature_columns,
            optimizer=lambda: tf.keras.optimizers.Adam(learning_rate=tf.compat.v1.train.exponential_decay(learning_rate=0.1,
            global_step=tf.compat.v1.train.get_global_step(), decay_steps=IT,decay_rate=0.96)))
#
classifier.train(input_fn=lambda: input_fn(X_train, y_train, training=True), max_steps = IT)
result = classifier.evaluate(input_fn=lambda: input_fn(X_test, y_test, training=False))
clear_output()
display(pd.DataFrame(result, index = ['']).round(4))

	accuracy	accuracy_baseline	auc	auc_precision_recall	average_loss	label/mean	loss	precision	prediction/mean	recall	global_step
	0.9532	0.6257	0.9554	0.9621	0.4645	0.6257	0.4645	0.9626	0.6166	0.9626	5000

ROC Curves

pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_test, y_test, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])    
ROC_Curve(y_test, probs, n_classes = len(Labels_dict), FS = 8)

Confusion Matrix

# Train
pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_train, y_train, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])
y_pred = np.argmax(probs, axis = 1).reshape(-1,1)
Reports_Train = pd.DataFrame(metrics.classification_report(y_train, y_pred, target_names=list(Labels_dict.values()),
                                                           output_dict=True)).T
CM_Train = metrics.confusion_matrix(y_train, y_pred)
# Test
pred_dicts = list(classifier.predict(input_fn=lambda: input_fn(X_test, y_test, training=False)))
clear_output()
probs = np.array([pred['probabilities'] for pred in pred_dicts])
y_pred = np.argmax(probs, axis = 1).reshape(-1,1)
Reports_Test = pd.DataFrame(metrics.classification_report(y_test, y_pred, target_names=list(Labels_dict.values()),
                                                          output_dict=True)).T
CM_Test = metrics.confusion_matrix(y_test, y_pred)

Reports_Train = Reports_Train.reset_index().rename(columns ={'index': 'Train Set'})
Reports_Test = Reports_Test.reset_index().rename(columns ={'index': 'Test Set'})
                                                 
display(Reports_Train.style.hide_index().set_properties(**{'background-color': 'HoneyDew', 'color': 'Black'}).\
        set_properties(subset=['Train Set'], **{'background-color': 'SeaGreen', 'color': 'White'}))
display(Reports_Test.style.hide_index().set_properties(**{'background-color': 'Azure', 'color': 'Black'}).\
        set_properties(subset=['Test Set'], **{'background-color': 'RoyalBlue', 'color': 'White'}))

PD = dict(FS = (10, 6), annot_kws = 14, shrink = .6, Labels = list(Labels_dict.values()))
Confusion_Mat(CM_Train, CM_Test, PD = PD, n_splits = None)

Train Set	precision	recall	f1-score	support
Malignant	1.000000	1.000000	1.000000	148.000000
Benign	1.000000	1.000000	1.000000	250.000000
accuracy	1.000000	1.000000	1.000000	1.000000
macro avg	1.000000	1.000000	1.000000	398.000000
weighted avg	1.000000	1.000000	1.000000	398.000000

Test Set	precision	recall	f1-score	support
Malignant	0.937500	0.937500	0.937500	64.000000
Benign	0.962617	0.962617	0.962617	107.000000
accuracy	0.953216	0.953216	0.953216	0.953216
macro avg	0.950058	0.950058	0.950058	171.000000
weighted avg	0.953216	0.953216	0.953216	171.000000

---

References

1. Regression analysis Wikipedia page
2. Tensorflow tutorials
3. W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on Electronic Imaging: Science and Technology, volume 1905, pages 861-870, San Jose, CA, 1993.
4. O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and prognosis via linear programming. Operations Research, 43(4), pages 570-577, July-August 1995.
5. W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) 163-171.
6. Online machine learning Wikipedia page
7. Learning rate Wikipedia page

---